The Math Beneath AI

What math do you need to understand how ChatGPT works? Vectors, matrices, calculus, probability, optimization — the four pillars of modern machine learning.

About 30 min·6 nodes

Progress0 / 6 (0%)

The path across the map

Select a card to move the map to that location.

STEP 1 · ConceptNo location

Vectors and Matrices

Mathematics that tables relationships and transforms directions, spaces, and data together. Chinese equation tables, Japanese and European determinant traditions, and nineteenth-century vector spaces and matrix algebra grew from different problems before becoming important computational languages in graphics, quantum theory, statistics, search, and machine learning.

↓Next step

STEP 2 · ConceptNo location

Calculus

The mathematics of change (derivatives) and accumulation (integrals).

↓Next step

STEP 3 · ConceptNo location

Probability

The mathematics of chance — from 17th-century gambling to modern AI.

↓Next step

STEP 4 · ConceptNo location

Statistics and Inference

The mathematics of reasoning from observed cases to a wider population, process, or effect. Its central task is not merely gathering more numbers but exposing who was counted, what was measured, and which comparisons and assumptions support a conclusion.

↓Next step

STEP 5 · ConceptNo location

Optimization

The mathematics of minimizing or maximizing a stated objective subject to constraints. An optimum exists only after “better” and “feasible” are specified; local versus global, exact versus approximate, computable versus socially desirable remain distinct.

↓Next step

STEP 6 · Concept1948Bell Labs· Discovery

Information Entropy

A bit-valued measure of average uncertainty in a probability distribution. Building on Nyquist and Hartley, Shannon’s 1948 theory treats source-coding and noisy-channel limits under distinct assumptions; it does not directly measure semantic depth or one file’s compressed size.

Intermediate → Advanced

Ready for advanced depth?

Unify similar-looking phenomena and examine why a claim fails when its hypotheses disappear.

Next takeaway · An explanation that includes its hypotheses

Open a advanced path